# ntegrals/10x

⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.

Repository: https://github.com/ntegrals/10x
Canonical: https://ross.abutalabs.com/products/10x
Homepage: https://try10x.co
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai-agents, anthropic, claude, claude-code, codex, coding-agent, continue, gemini-cli, open-code
Last push: 2026-01-05T01:46:15+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 60, release rhythm 21, longevity 72
- inputs: {"age_days": 1014, "days_push": 241, "days_rel": 317, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1360, forks 113 (observed 2026-08-28T04:04:29.961042+00:00)

## What it is
10x is an open-source terminal-based AI coding agent that chains multiple LLM models through multi-step 'Superpowers' workflows with smart model routing. It supports BYOK across OpenAI, Anthropic, Google, and local models, with file system access, shell integration, and persistent sessions.

## Use cases
- ai coding agent in the terminal
- automate code review and refactoring with llms
- route coding tasks to cheapest capable ai model
- generate pull request descriptions from git changes
- self-hosted claude code alternative with own api keys
- generate test suites with ai
- debug code step by step with ai assistance

## When to choose
- you want an open-source, BYOK alternative to Claude Code or Copilot
- you want multi-step AI workflows chaining different model tiers
- you prefer a terminal workflow without IDE plugins
- you need cost tracking and control over which models handle which tasks

## When to avoid
- you need a fully offline coding assistant without any LLM API access
- you prefer IDE-integrated autocomplete-style assistance
- you want a mature tool with a long track record - the project is very new (v0.0.7)

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, prompt-engineering, developer-tools, cli, code-review, testing
- domain: developer-tools, artificial-intelligence, large-language-models
- platform: cli, cross-platform
- tags: ai-coding-agent, byok, model-routing, claude-code-alternative, terminal-ai, multi-step-workflows, openrouter, command-line, ai-agents, macos, linux, nodejs

## Member repositories
- ntegrals/10x (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.961042+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:41:39.997040+00:00, confidence not recorded.
  - readme: https://github.com/ntegrals/10x (fetched 2026-08-28T04:04:29.961042+00:00, sha 913435e0dbef)
  - homepage: https://try10x.co (fetched 2026-08-29T11:59:53.063375+00:00, sha a65f9f3785c0)
  - site_page: https://try10x.co/pricing (fetched 2026-08-29T11:59:53.075702+00:00, sha 14673355fe5f)
  - site_page: https://try10x.co/auth/signin (fetched 2026-08-29T11:59:53.077483+00:00, sha bf8c65e7936f)
- Data as of 2026-08-30T08:39:29.467469+00:00.